Graph Triple Attention Network: A Decoupled Perspective

TL;DR

This paper introduces DeGTA, a decoupled graph attention network that separately models multi-view attention components and local-global interactions, leading to improved interpretability and state-of-the-art results in graph tasks.

Contribution

The paper proposes a novel decoupled perspective for Graph Transformers, enabling flexible, interpretable, and adaptive multi-view attention modeling with superior performance.

Findings

DeGTA achieves state-of-the-art results on multiple graph datasets.

Decoupling improves interpretability and performance.

Ablation studies confirm the importance of decoupling components.

Abstract

Graph Transformers (GTs) have recently achieved significant success in the graph domain by effectively capturing both long-range dependencies and graph inductive biases. However, these methods face two primary challenges: (1) multi-view chaos, which results from coupling multi-view information (positional, structural, attribute), thereby impeding flexible usage and the interpretability of the propagation process. (2) local-global chaos, which arises from coupling local message passing with global attention, leading to issues of overfitting and over-globalizing. To address these challenges, we propose a high-level decoupled perspective of GTs, breaking them down into three components and two interaction levels: positional attention, structural attention, and attribute attention, alongside local and global interaction. Based on this decoupled perspective, we design a decoupled graph triple attention network named DeGTA, which separately computes multi-view attentions and adaptively integrates multi-view local and global information. This approach offers three key advantages: enhanced interpretability, flexible design, and adaptive integration of local and global information. Through extensive experiments, DeGTA achieves state-of-the-art performance across various datasets and tasks, including node classification and graph classification. Comprehensive ablation studies demonstrate that decoupling is essential for improving performance and enhancing interpretability. Our code is available at: https://github.com/wangxiaotang0906/DeGTA